Promoted and joined the GDC (Google Distributed Cloud) AI Performance team in August 2025, with a focus on Gemini inference for GPUs. Researching and implementing optimizations for better model latency and quality across air-gapped, on-premise, and GKE environments.
Worked on the GKE (Google Kubernetes Engine) AI Infrastructure team from Oct 2023 - August 2025. Launched new GPU/TPU accelerators and developed new fleet maintenance features for improved training and inference reliability.